社会层面 · privacy论文趋势 2023–2026

主要结论

• 社会层面 · privacy论文从 2023 年的 21 篇增长到 2026 年的 138 篇，三年间扩大到约 6.6 倍。
• NeurIPS 是发社会层面 · privacy论文最多的会议，2023–2026 年共 215 篇，占四个会议总量的 50%。
• 交叉方向里涨得最快的是社会层面 · accountability transparency and interpretability：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 93 篇。
• 在「对齐与负责任 AI」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的社会层面 · safety是 93 倍，社会层面 · privacy是 6.6 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026Assessing Per-Sample Membership Inference Vulnerability without Retraining
• ICML 2026Accuracy-First Rényi Differential Privacy and Post-Processing Immunity
• ICLR 2026Mitigating Privacy Risk via Forget Set-Free Unlearning
• CVPR 2026Protego User-Centric Pose-Invariant Privacy Protection Against Face Recognition-Induced Digital Footprint
• NeurIPS 2025A Generalized Binary Tree Mechanism for Private Approximation of All-Pair Shortest Distances
• ICML 2025Breaking the $n^{1.5}$ Additive Error Barrier for Private and Efficient Graph Sparsification via Private Expander Decomposition
• ICLR 2025Machine Unlearning via Simulated Oracle Matching
• CVPR 2025Enhancing Facial Privacy Protection via Weakening Diffusion Purification
• NeurIPS 2024Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences
• ICML 2024Privacy Preserving Adaptive Experiment Design
• ICLR 2024Beyond Memorization: Violating Privacy via Inference with Large Language Models
• CVPR 2024Validating Privacy-Preserving Face Recognition under a Minimum Assumption
• NeurIPS 2023Faster approximate subgraph counts with privacy
• ICML 2023GuardHFL: Privacy Guardian for Heterogeneous Federated Learning
• ICLR 2023Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models
• CVPR 2023Privacy-Preserving Representations Are Not Enough: Recovering Scene Content From Camera Poses
• NeurIPS 2026Asymmetric Invertible Threat: Learning Reversible Privacy Defense for Face Recognition
• ICML 2026Accurate, Private, Secure, Federated U-statistics with Higher Degree
• ICLR 2026Measuring Physical-World Privacy Awareness of Large Language Models: An Evaluation Benchmark
• CVPR 2026LDP-Slicing Local Differential Privacy for Images via Randomized Bit-Plane Slicing

全部社会层面 · privacy论文

共 215 篇，第 3 / 5 页

101. NeurIPS 2025Purifying Approximate Differential Privacy with Randomized Post-processing
102. NeurIPS 2025Query-Efficient Locally Private Hypothesis Selection via the Scheffe Graph
103. NeurIPS 2025Rethinking Fair Federated Learning from Parameter and Client View
104. NeurIPS 2025Rethinking the Role of Verbatim Memorization in LLM Privacy
105. NeurIPS 2025Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions
106. NeurIPS 2025RUAGO: Effective and Practical Retain-Free Unlearning via Adversarial Attack and OOD Generator
107. NeurIPS 2025Second-Order Convergence in Private Stochastic Non-Convex Optimization
108. NeurIPS 2025Secure and Confidential Certificates of Online Fairness
109. NeurIPS 2025Sequentially Auditing Differential Privacy
110. NeurIPS 2025Setting $\varepsilon$ is not the Issue in Differential Privacy
111. NeurIPS 2025Sketched Gaussian Mechanism for Private Federated Learning
112. NeurIPS 2025Subgraph Federated Learning via Spectral Methods
113. NeurIPS 2025Sum Estimation under Personalized Local Differential Privacy
114. NeurIPS 2025Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries
115. NeurIPS 2025The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples
116. NeurIPS 2025Time-uniform and Asymptotic Confidence Sequence of Quantile under Local Differential Privacy
117. NeurIPS 2025TokenSwap: A Lightweight Method to Disrupt Memorized Sequences in LLMs
118. NeurIPS 2025Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
119. NeurIPS 2025Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction Attacks
120. NeurIPS 2025Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy
121. NeurIPS 2025Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM
122. NeurIPS 2025Versatile Transferable Unlearnable Example Generator
123. NeurIPS 2025⁠When Data Can't Meet: Estimating Correlation Across Privacy Barriers
124. NeurIPS 2025You Only Communicate Once: One-shot Federated Low-Rank Adaptation of MLLM
125. NeurIPS 2024A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy
126. NeurIPS 2024A Synthetic Dataset for Personal Attribute Inference
127. NeurIPS 2024Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences
128. NeurIPS 2024Attack-Aware Noise Calibration for Differential Privacy
129. NeurIPS 2024Auditing Privacy Mechanisms via Label Inference Attacks
130. NeurIPS 2024Banded Square Root Matrix Factorization for Differentially Private Model Training
131. NeurIPS 2024Can Graph Neural Networks Expose Training Data Properties? An Efficient Risk Assessment Approach
132. NeurIPS 2024Certified Machine Unlearning via Noisy Stochastic Gradient Descent
133. NeurIPS 2024Continual Counting with Gradual Privacy Expiration
134. NeurIPS 2024Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature
135. NeurIPS 2024DAGER: Exact Gradient Inversion for Large Language Models
136. NeurIPS 2024DataStealing: Steal Data from Diffusion Models in Federated Learning with Multiple Trojans
137. NeurIPS 2024Déjà Vu Memorization in Vision–Language Models
138. NeurIPS 2024Differential Privacy in Scalable General Kernel Learning via $K$-means Nystr{\"o}m Random Features
139. NeurIPS 2024Differentially Private Equivalence Testing for Continuous Distributions and Applications
140. NeurIPS 2024Differentially Private Optimization with Sparse Gradients
141. NeurIPS 2024Differentially Private Reinforcement Learning with Self-Play
142. NeurIPS 2024Differentially Private Set Representations
143. NeurIPS 2024Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement
144. NeurIPS 2024Dimension-free Private Mean Estimation for Anisotropic Distributions
145. NeurIPS 2024Disentangled Style Domain for Implicit $z$-Watermark Towards Copyright Protection
146. NeurIPS 2024DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction
147. NeurIPS 2024Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning
148. NeurIPS 2024Efficient and Private Marginal Reconstruction with Local Non-Negativity
149. NeurIPS 2024Exactly Minimax-Optimal Locally Differentially Private Sampling
150. NeurIPS 2024Faster Algorithms for User-Level Private Stochastic Convex Optimization

常见问题

2023–2026 年四大会议一共有多少篇社会层面 · privacy论文？

共 431 篇，按年份分别是 2023 年 21 篇、2024 年 117 篇、2025 年 155 篇、2026 年 138 篇。

NeurIPS 2026 有多少篇社会层面 · privacy论文？

NeurIPS 2026 有 44 篇社会层面 · privacy论文，上一届是 80 篇。

ICLR 2026 有多少篇社会层面 · privacy论文？

ICLR 2026 有 2 篇社会层面 · privacy论文，上一届是 2 篇。

ICML 2026 有多少篇社会层面 · privacy论文？

ICML 2026 有 90 篇社会层面 · privacy论文，上一届是 71 篇。

CVPR 2026 有多少篇社会层面 · privacy论文？

CVPR 2026 有 2 篇社会层面 · privacy论文，上一届是 2 篇。

哪个会议的社会层面 · privacy论文最多？

NeurIPS，2023–2026 年共 215 篇。